AI Desk · AI FingerprintingWithdrawn *

DeepSeek: DeepSeek V4 Flash 0731 (batch)

deepseek/deepseek-v4-flash-0731:batch · DeepSeekDeclared and measured agree

Tokenizer group (measured): DeepSeek
Declared tokenizer tag: DeepSeek
Entered catalogue: 31 July 2026
Measurement: Variant: inherits its base model’s measurement
Evidence confidence: High

Why high: inherited from deepseek/deepseek-v4-flash-0731: a serving variant shares its base model's tokenizer.

Evidence

✓ inherited from deepseek/deepseek-v4-flash-0731: a serving variant shares its base model's tokenizer

Compare with DeepSeek: DeepSeek V4 Flash 0731

Report a correction

This entry is a serving variant of DeepSeek: DeepSeek V4 Flash 0731. A variant shares its base model's tokenizer by construction, so the measurement lives on the base record and this page inherits it.

Identity statement

DeepSeek: DeepSeek V4 Flash 0731 (batch) is DeepSeek's model, and its measured tokenizer sits in DeepSeek's own signature group alongside its sibling models. No other maker's measured model shares it so far.

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Not measured yet	we measured it
How its API is set up	A combination of settings no other listing in the catalogue uses	api_431ca768
How much it can read and write	Reads up to 1,048,576 tokens at onceOpenRouter's listing shows 943,718 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum. DeepSeek's own API reference caps max_tokens at 384K, 393,216 tokens, for deepseek-flash and deepseek-v4-pro.	its own listing
Whether it thinks before answering	Reasons when asked to, at max, high, low, high by default	its own listing

Declared record

What the catalogue claims about this model

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Modalities: text->text
Declared tokenizer: DeepSeek
Prompt price: $0.11 / M tokens
Completion price: $0.33 / M tokens

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

defaults: {}

Catalogue entry Weights on Hugging Face

History

Every observation, kept as taken

31 July 2026Enters the OpenRouter catalogue declared as DeepSeek.

* DeepSeek: DeepSeek V4 Flash 0731 (batch) no longer appears in the OpenRouter catalogue, first absent from the snapshot of 5 October 2026. The record stays because the measurements above were real when they were taken and this address has been published.